archive-edu.com » EDU » M » MIT.EDU

Total: 993

Choose link from "Titles, links and description words view":

Or switch to "Titles and links view".
  • CSAIL Calendar: The Simulation Engine of the Brain
    In the Media Events Calendar News in Exhibit Awards Event Calendar The Simulation Engine of th Seminar Series List The Simulation Engine of th Edit Event Cancel Event Preview Reminder Send Reminder Other events happening in March 2012 The Simulation Engine of the Brain Speaker Dr Demis Hassabis Wellcome Trust Research Fellow Gatsby Computational Neuroscience Unit UCL Date Wednesday March 28 2012 Time 4 00 PM to 5 00 PM Refreshments No Refreshments Offered Location McGovern Seminar Room MIT 46 3189 Host Lorenzo Rosasco IIT MIT CBCL BCS Dept Contact Kathleen Sullivan 617 253 0551 kdsulliv mit edu Relevant URL http cbcl mit edu http cbcl mit edu Reminders to seminars csail mit edu Reminder Subject TALK The Simulation Engine of the Brain In daily life people frequently imagine future events such as how a dinner date might unfold Such simulations are typically mentally played out in a rich spatial context and often involve the presence of people and their concomitant thoughts and behaviors It has been proposed that a common core brain network supports the simulation of past future or hypothetical experiences I will describe a series of fMRI and patient studies exploring the neural mechanisms that underpin this

    Original URL path: https://calendar.csail.mit.edu/events/3266 (2015-06-22)
    Open archived version from archive


  • CSAIL Calendar: Automatically Learning the Structure of Spoken Language Without Supervision
    2012 Automatically Learning the Structure of Spoken Language Without Supervision Speaker Aren Jensen Human Language Technology Center of Excellence and Center for Language and Speech Processing Johns Date Monday May 07 2012 Time 3 00 PM to 4 00 PM Refreshments No Refreshments Offered Location Patil Kiva Seminar Rm Stata Bldg MIT 32 G449 Host Lorenzo Rosasco IIT MIT CBCL BCS Dept Contact Kathleen Sullivan 617 253 0551 kdsulliv mit edu Relevant URL http cbcl mit edu Reminders to seminars csail mit edu Reminder Subject TALK Automatically Learning the Structure of Spoken Language Without Supervision Abstract The dominant paradigm in the speech recognition community for the past four decades has been to train automatic systems with as much transcribed data we can get our greedy hands on This strategy has led to the development of highly accurate systems that have finally found a place in our daily lives in the form of popular applications such as Apple iPhone s Siri An unfortunate consequence of this trajectory however is that state of the art recognition performance can only be achieved on languages and domains for which vast transcribed training resources either exist or can be easily obtained Meanwhile with public internet

    Original URL path: https://calendar.csail.mit.edu/events/3321 (2015-06-22)
    Open archived version from archive

  • CSAIL Calendar: Image Classification using Super-Vector Coding
    Reminder Other events happening in September 2011 Image Classification using Super Vector Coding Speaker Kai Yu NEC Labs Date Wednesday September 07 2011 Time 12 00 PM to 1 00 PM Refreshments No Refreshments Offered Location McGovern Seminar Room MIT 46 3189 Host Lorenzo Rosasco Istituto Italiano di Tecnologia CBCL MIT Contact Kathleen Sullivan 617 253 0551 kdsulliv mit edu Relevant URL http isquared mit edu Reminders to seminars csail mit edu Reminder Subject TALK Image Classification using Super Vector Coding Abstract In this talk I will share our experience about large scale image recognition using nonlinear encoding of image patches We worked on extending sparse coding to a broader family of simple coding methods in particular super vector coding which explore the geometrical structure of sensory image data The coding of image local features gives rise to significantly better features which enable simple linear classifiers to produce stronger results and also scale much better than nonlinear SVMs using Chi square or intersection kernels The methods achieved state of the art results on a range of challenging image classification tasks including Caltech 101 Caltech 256 PASCAL VOC and ImageNet Short bio Kai Yu is the head of Media Analytics Department

    Original URL path: https://calendar.csail.mit.edu/events/3033 (2015-06-22)
    Open archived version from archive

  • CSAIL Calendar: Classification by Invariant Scattering
    Student Spotlights Contact Media Alumni Welcome CALENDAR You have 0 future meetings news Events 2013 News CSAIL Spotlights In the Media Events Calendar News in Exhibit Awards Event Calendar Classification by Invariant Seminar Series List Classification by Invariant Edit Event Cancel Event Preview Reminder Send Reminder Other events happening in September 2010 Classification by Invariant Scattering Speaker Dr Stephane Mallat Applied Mathematics Ecole Polytechnique Paris Date Friday September 10 2010 Time 2 00 PM to 3 00 PM Refreshments No Refreshments Offered Location Singleton Auditorium MIT 46 3002 Host Prof Tomaso A Poggio CBCL McGovern Inst BCS Dept CSAIL Contact Kathleen D Sullivan 617 253 0551 kdsulliv mit edu Relevant URL http cbcl mit edu http cbcl mit edu Reminders to seminars csail mit edu Reminder Subject TALK Classification by Invariant Scattering Abstract Signal classes are usually invariant to groups of operators such as translations or scalings and to larger Lie groups of deformations Classification thus requires finding informative invariants Invariants are also at the core of quantum physics through Gauge theories We introduce non linear invariant operators similar to quantum scattering These operators have small commutators with elastic deformations and provide new representations of stationary processes Their computational architecture

    Original URL path: https://calendar.csail.mit.edu/events/2687 (2015-06-22)
    Open archived version from archive

  • CSAIL Calendar: I2 Seminar Series: Social Intelligence
    W Lo Thomas W Malone Alex P Pentland MIT Date Wednesday September 15 2010 Time 4 15 PM to 5 15 PM Refreshments No Refreshments Offered Location Singleton Auditorium MIT 46 3002 Host Prof Tomaso A Poggio CBCL McGovern Inst BCS Dept CSAIL Contact Kathleen D Sullivan 617 253 0551 kdsulliv mit edu Relevant URL http isquared mit edu Reminders to seminars csail mit edu Reminder Subject TALK I2 Seminar Series Social Intelligence Three brief talks o The Origin of Behavior Andrew W Lo o Collective Intelligence Thomas W Malone o Computational Social Science Alex P Pentland followed by a panel discussion This event is organized by the I2 Social Intelligence Working Group One of the most fundamental manifestations of human intelligence is the ability to engage in social interactions communication coordination and collaboration so as to overcome challenges and attain goals that would be impossible for any single individual While social intelligence is found among many species human social intelligence is unique in its scale and complexity The Social Intelligence Working Group focuses on how this social intelligence is achieved both at the level of individuals interacting with each other and at the level of groups facing common challenges

    Original URL path: https://calendar.csail.mit.edu/events/2706 (2015-06-22)
    Open archived version from archive

  • CSAIL Calendar: Evolution of cooperation
    CSAIL Contact Kathleen D Sullivan 617 253 0551 kdsulliv mit edu Relevant URL http isquared mit edu http isquared mit edu Reminders to seminars csail mit edu Reminder Subject TALK I 2 Seminar Series Evolution of cooperation I 2 Seminar Series Evolution of cooperation Abstract Cooperation means that one individual pays a cost for another to receive a benefit Cost and benefit are measured in terms of reproductive success Cooperation is required for construction in evolution genomes cells multi cellular organisms animal and human societies are consequences of cooperation Cooperative behavior is at variance with natural selection Why should we help competitors I present five mechanisms for the evolution of cooperation kin selection direct reciprocity indirect reciprocity spatial selection and group selection Direct reciprocity means there are repeated interactions between the same two individuals and my behavior towards you depends on what you have done to me Indirect reciprocity means there are repeated interactions within a group and my behavior towards you also depends on what you have done to others Indirect reciprocity is the key mechanism for understanding pro social behavior among humans and has provided the right selection pressure for the evolution of social intelligence and human language Further reading Nowak MA 2006 Evolutionary Dynamics Harvard University Press Nowak MA 2006 Five rules for the evolution of cooperation Science 314 1560 1563 Nowak MA Tarnita CE Wilson EO 2010 The evolution of eusociality Nature 466 1057 1062 Speaker Bio Martin A Nowak is Professor of Biology and of Mathematics at Harvard University and Director of Harvard s Program for Evolutionary Dynamics Dr Nowak works on the mathematical description of evolutionary processes including the evolution of cooperation and human language the dynamics of virus infections and human cancer His major discoveries include the mechanism of HIV disease progression 1991

    Original URL path: https://calendar.csail.mit.edu/events/2747 (2015-06-22)
    Open archived version from archive

  • CSAIL Calendar: Linear and piecewise linear data analysis
    and piecewise linear Seminar Series List Linear and piecewise linear Edit Event Cancel Event Preview Reminder Send Reminder Other events happening in February 2011 Linear and piecewise linear data analysis Speaker Arthur Szlam Courant Institute of Mathematical Sciences NYU Date Thursday February 10 2011 Time 4 30 PM to 5 30 PM Refreshments No Refreshments Offered Location Patil Kiva Sem Rm 32 G449 Host Lorenzo Rosasco Istituto Italiano di Tecnologia CBCL MIT Contact Kathleen Sullivan 617 253 0551 kdsulliv mit edu Relevant URL http cbcl mit edu http cbcl mit edu Reminders to seminars csail mit edu Reminder Subject TALK Linear and piecewise linear data analysis The seminar is co hosted by the Brain and Machine Seminar Series Image and Computing Seminar Series Abstract Many data sets arising from signal processing or machine learning problems can be approximately modeled as a union of K low dimensional linear sets In this talk I will start by discussing the case K 1 which remains a surprisingly active area of research despite more than a hundred years of history and a good understanding of the mathematics of the problem for many notions of approximately and low For larger values of K although heuristic

    Original URL path: https://calendar.csail.mit.edu/events/2826 (2015-06-22)
    Open archived version from archive

  • CSAIL Calendar: Sparse and Smooth: An optimal convex relaxation for high-dimensional kernel regression
    Berkeley Date Wednesday February 23 2011 Time 4 30 PM to 5 30 PM Refreshments No Refreshments Offered Location Star Sem Rm Stata D463 Host Lorenzo Rosasco Istituto Italiano di Tecnologia CBCL MIT Contact Kathleen Sullivan 617 253 0551 kdsulliv mit edu Relevant URL http cbcl mit edu http cbcl mit edu Reminders to seminars csail mit edu Reminder Subject TALK Sparse and Smooth An optimal convex relaxation for high dimensional kernel regression Abstract The problem of non parametric regression is well known to suffer from a severe curse of dimensionality in that the required sample size grows exponentially with the dimension d Consequently the success of any successful learning procedure in high dimensions depends some kind of low dimensional structure This talk focuses on non parametric estimation within the family of sparse additive models which consist of sums of univariate functions over s unknown co ordinates We derive a simple and intuitive convex relaxation for estimating sparse additive models described by reproducing kernel Hilbert spaces The method involves solving a second order cone program SOCP and so scales well to large scale problems Working within a high dimensional framework that allows both the dimension d and sparsity s to

    Original URL path: https://calendar.csail.mit.edu/events/2852 (2015-06-22)
    Open archived version from archive



  •